CN117012053A - Post-optimization method, system and storage medium for parking space detection point - Google Patents
Post-optimization method, system and storage medium for parking space detection point Download PDFInfo
- Publication number
- CN117012053A CN117012053A CN202311267169.9A CN202311267169A CN117012053A CN 117012053 A CN117012053 A CN 117012053A CN 202311267169 A CN202311267169 A CN 202311267169A CN 117012053 A CN117012053 A CN 117012053A
- Authority
- CN
- China
- Prior art keywords
- parking
- vehicle
- data information
- spots
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a post-optimization method, a system and a storage medium for parking space detection points, wherein the method comprises the following steps: q1. collecting data information of parking spots under a world coordinate system in the same parking lot, wherein the data information of the parking spots comprises coordinate data information of the vehicle spots and orientation angle data information of the vehicle spots, clustering and roughly grouping the parking spots according to the orientation angle data information of the vehicle spots, and outputting rough grouping data information of the vehicle spots; and Q2, inputting the coordinate data information of the vehicle position into a vehicle position same-row offset distance algorithm to carry out fine grouping on the vehicle position based on the rough grouping data information of the vehicle position, and outputting the fine grouping data information of the vehicle position. The application not only provides a multi-parking-space grouping optimization method after sensing and fusing to obtain parking space data, and provides more accurate and more reasonable parking space output, but also provides stable and accurate parking space data support for functional modules such as path planning and the like in a parking automatic driving system.
Description
Technical Field
The application relates to the technical field of automatic driving of vehicles, in particular to a post-optimization method, a system and a storage medium for parking space detection points.
Background
The updating iteration of the automatic parking system in automatic driving is rapid from L2 to L4, and the functions of the automatic parking system are continuously updated to be more efficient and safer to replace people to complete the parking function. The main function development direction is as follows, APA assists in parking, which is a common parking auxiliary system in life, and the vehicle position is detected by using a picture of a BEV view angle formed by a looking-around camera at low-speed cruising, so that a driver is helped to detect an unoccupied parking space which can be parked in. The driver selects a parking space to automatically park, RPA remotely parks, the function reaches the automatic driving level of L2+ and is added with application related to vehicle Bluetooth or 4G remote mobile phone control on the basis of APA, the driver can remotely control the parking in the vehicle without parking, AVP automatically parks for passengers, the function reaches the automatic driving level of L4, and a front-view camera is added on the basis of a looking-around camera and an ultrasonic radar.
The development of automatic parking systems is becoming more mature and gradually developed. From the application of simple vehicle periphery ultrasonic radar, the introduction of mobile phones and vehicle Bluetooth provides more abundant parking functions, the introduction of vision BEV technology and the development of deep learning, and the development of multi-sensor fusion technology such as looking-around cameras, ultrasonic millimeter waves and wave radar. Each function iteration is not separated from the maturity of the vehicle-mounted sensor technology, the acceleration of calculation force, the algorithm and the communication technology. As communication protocols, sensor technology, infrastructure become more sophisticated, automobiles will become more intelligent. In the future, the automobile may not be a simple travel partner, but rather a rapid life start.
The most important in the parking scene is the detection of the parking spaces, the current optimization algorithm for the detection of the parking spaces mainly relates to a filtering algorithm, and the simpler optimization algorithm such as a KALMAN algorithm mainly carries out smooth filtering on the parking space points, does not consider the integral data characteristics of the parking spaces, and optimizes the parking space data by internal association among the parking spaces.
In the prior art, patent (application number: 202211012090.7) discloses a parking space detection method and a tracking method thereof, a parking space detection device and a computer readable storage medium, wherein the parking space detection method and the tracking method thereof comprise the steps of S1, acquiring a looking-around picture of a parking space, extracting low-level semantic features and high-level semantic features of the looking-around picture, fusing the low-level semantic features and the high-level semantic features, and acquiring fusion features; s2, decoding the fusion characteristics to obtain a plurality of groups of branches; s3, reasoning is carried out according to the branches to obtain all detected parking spaces. But in this scheme the parking stall detection range under the BEV is little and because look around the camera generally all is fish eye camera, because of the error that factors such as distortion necessarily lead to the detection precision is too big, and the error that leads to the overall performance of parking stall at the in-process parking stall precision of searching the parking stall is inconsistent, can obviously see the holistic confusion of parking stall that the precision of parking stall leads to.
In the prior art, patent (application number: 201910566090.3) discloses a vision-based right-direction empty parking space and a parking space line detection method in a parking process, and the method comprises the following steps: first step, the image that will detect the parking stall camera and gather is converted into the form of aerial view from normal visual angle, and the parking stall of being convenient for detects. Step two, preprocessing the image; thirdly, extracting features of parking spaces; fourth, detecting a parking space; and fifthly, converting coordinates and outputting parking space information. However, in the scheme, the internal relation between the parking spaces and the parking spaces is not considered, for example, real parking spaces are all drawn in groups, and the same type of parking space arrangement has a specific structure and sequence and has an internal logic relation.
Disclosure of Invention
In view of the defects in the prior art, the application provides a post-optimization method, a post-optimization system and a storage medium for parking space monitoring points, which not only provides a multi-parking space grouping optimization method after sensing and fusing to obtain parking space data, but also provides more accurate and more reasonable parking space output, and gives stable and accurate parking space data support to functional modules such as path planning and the like in a parking automatic driving system.
In order to achieve the above object and other related objects, the present application provides the following technical solutions:
a post-optimization method for a parking spot detection point, the method comprising:
q1. collecting data information of parking spots under a world coordinate system in the same parking lot, wherein the data information of the parking spots comprises coordinate data information of the vehicle spots and orientation angle data information of the vehicle spots, clustering and roughly grouping the parking spots according to the orientation angle data information of the vehicle spots, and outputting rough grouping data information of the vehicle spots;
q2, inputting the coordinate data information of the vehicle position into a vehicle position same-row offset distance algorithm to carry out fine grouping on the vehicle position based on the rough grouping data information of the vehicle position, and outputting the fine grouping data information of the vehicle position;
q3. based on the refined grouping data information of the parking spots, performing linear least square fitting on two near car spots of all the parking spots in the same group, and outputting fitting linear data information of the parking spots in the same group;
and Q4, optimizing the coordinate data information of the parking spots, the orientation angle data information of the vehicle spots and the central point coordinate data information of the vehicle spots based on the fitting straight line data information of the parking spots in the same group, and outputting the optimized parking spot data information.
Further, in step Q1, the step of clustering the parking space points according to the orientation angle data information of the vehicle positions includes that the parking space points are roughly grouped according to the orientation angles of the parking spaces, the orientation angles of the parking spaces of the same parking space type are consistent, and the parking space type includes a vertical parking space, a horizontal parking space and an oblique parking space.
Further, in step Q2, the vehicle-site in-line offset distance algorithm includes:
q21 obtaining two coordinates P of the near vehicle point in the width direction of the ith vehicle position point according to the coordinate data information of the vehicle position point i1 (X i1 ,Y i1 0), and P i2 (X i2 ,Y i2 0) and two near-vehicle-point coordinates P in the width direction of the jth parking spot j1 (X j1 ,Y j1 0), and P j2 (X j2 ,Y j2 ,0)；
Q22 based on the two near-vehicle-point coordinates P in the width direction of the ith vehicle-position point i1 And P i2 Two near-vehicle-point coordinates P in width direction of jth parking spot j1 And P j2 Two near vehicle points P of the jth vehicle point are established j1 And P j2 Respectively to line segment P i1 And P i2 Projection distance function d of (2) j1 And d j2 ，
，/>，
Wherein W is two near-vehicle point coordinates P i1 And P i2 Distance L of (2) 11 、L 12 、L 21 And L 22 Respectively the parameters of projection distance S 1 And S is 2 Is a distance difference factor;
q23 based on the projectionDistance function d j1 And d j2 Setting a preset threshold value, if d j1 And d j2 The values of the (b) are smaller than the preset threshold value, and the ith vehicle position and the jth vehicle position are the same row of parking spaces.
Further, the precise grouping data information of the parking spots is the parking spot data information of the same row, wherein the orientation angles of the parking spots in the same grouping are consistent.
Further, in step Q3, the performing a straight line minimum fitting on two near points of the parking spaces in the same group includes:
q31, acquiring near-vehicle-point coordinate data information of vehicle points in the same group based on the precise group data information of the vehicle points;
q32 based on the coordinate data information of the near points of the same group of vehicle points, adopting a least square algorithm to perform straight line fitting to obtain the slope k and intercept b of the fitted straight line,
，
，
wherein N is the number of car-loci of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The coordinates of the near vehicle point of the ith vehicle point;
and Q33, obtaining fitting straight line data information of the parking spaces in the same group based on the slope k and the intercept b of the fitting straight line.
Further, in step Q4, the optimized parking spot data information includes coordinates of a near spot of the optimized parking spotAnd->，
，/>，
Wherein k is the slope of the fitting line in the fitting line data information of the parking spaces of the same group, b is the intercept of the fitting line in the fitting line data information of the parking spaces of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The near car point coordinates of the i-th car point.
Further, the optimized parking spot data information also comprises a parking spot orientation angle theta of the optimized vehicle spot,
，
wherein,and->And the near-vehicle-point coordinates of the optimized vehicle-point are obtained.
Further, the optimized parking spot data information further comprises far spot coordinates of the optimized parking spotAnd->Parking space center coordinates +.>，
，/>，
，
Wherein,and->For the near-vehicle-point coordinates of the optimized vehicle-point, θ is the parking-space orientation angle of the optimized vehicle-point, and L is +.>And->Is a distance between the two.
To achieve the above and other related objects, the present application also provides a post-optimization system for a parking spot, including a computer device programmed or configured to perform the steps of the post-optimization method for a parking spot according to any one of the above.
To achieve the above and other related objects, the present application also provides a computer-readable storage medium having stored thereon a computer program programmed or configured to perform the post-optimization method of the parking spot detection point of any one of the above.
The application has the following positive effects:
1. in an automatic driving parking scene, one of the data about the success rate of parking into the parking space is the parking space data, and after the parking space data are obtained through sensing fusion, the method for optimizing the multi-parking space grouping is provided, and more accurate and more reasonable parking space output is provided.
2. According to the application, from the angle of actual parking space data, the law of an actual field is considered, the data characteristics, the structural characteristics and the inherent mathematical logic of the same group of parking spaces are analyzed, the grouping optimization method for multiple parking spaces is used, reasonable, smooth and orderly parking spaces are provided in an interactive interface and displayed to clients, and stable and accurate parking space data support of functional modules such as path planning and the like is provided in a parking automatic driving system.
Drawings
FIG. 1 is a schematic flow chart of the method of the application.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1: as shown in fig. 1, a post-optimization method for a parking space detection point includes:
q1. collecting data information of parking spots under a world coordinate system in the same parking lot, wherein the data information of the parking spots comprises coordinate data information of the vehicle spots and orientation angle data information of the vehicle spots, clustering and roughly grouping the parking spots according to the orientation angle data information of the vehicle spots, and outputting rough grouping data information of the vehicle spots;
q2, inputting the coordinate data information of the vehicle position into a vehicle position same-row offset distance algorithm to carry out fine grouping on the vehicle position based on the rough grouping data information of the vehicle position, and outputting the fine grouping data information of the vehicle position;
q3. based on the refined grouping data information of the parking spots, performing linear least square fitting on two near car spots of all the parking spots in the same group, and outputting fitting linear data information of the parking spots in the same group;
and Q4, optimizing the coordinate data information of the parking spots, the orientation angle data information of the vehicle spots and the central point coordinate data information of the vehicle spots based on the fitting straight line data information of the parking spots in the same group, and outputting the optimized parking spot data information.
In this embodiment, in step Q1, the clustering coarse grouping is performed on the parking spots according to the orientation angle data information of the parking spots, so that the coarse grouping is performed according to the orientation angles of the parking spots, the orientation angles of the parking spots of the same parking spot type are consistent, and the parking spot type includes a vertical parking spot, a horizontal parking spot and an oblique parking spot.
In this embodiment, in step Q2, the vehicle-site in-line offset distance algorithm includes:
q21 obtaining two coordinates P of the near vehicle point in the width direction of the ith vehicle position point according to the coordinate data information of the vehicle position point i1 (X i1 ,Y i1 0), and P i2 (X i2 ,Y i2 0) and two near-vehicle-point coordinates P in the width direction of the jth parking spot j1 (X j1 ,Y j1 0), and P j2 (X j2 ,Y j2 ,0)；
Q22 based on the two near-vehicle-point coordinates P in the width direction of the ith vehicle-position point i1 And P i2 Two near-vehicle-point coordinates P in width direction of jth parking spot j1 And P j2 Two near vehicle points P of the jth vehicle point are established j1 And P j2 Respectively to line segment P i1 And P i2 Projection distance function d of (2) j1 And d j2 ，
，/>，
Wherein W is two near-vehicle point coordinates P i1 And P i2 Distance L of (2) 11 、L 12 、L 21 And L 22 Respectively the parameters of projection distance S 1 And S is 2 Is a distance difference factor;
q23 based on the projection distance function d j1 And d j2 Setting a preset threshold value, if d j1 And d j2 The values of the (b) are smaller than the preset threshold value, and the ith vehicle position and the jth vehicle position are the same row of parking spaces.
In this embodiment, the fine grouping data information of the parking spots is parking spot data information of the same row, where the orientation angles of the parking spots in the same group are identical.
Example 2: the present application is further illustrated and described below based on a post-optimization method for a parking spot detection point in embodiment 1.
As shown in fig. 1, a post-optimization method for a parking space detection point includes:
q1. collecting data information of parking spots under a world coordinate system in the same parking lot, wherein the data information of the parking spots comprises coordinate data information of the vehicle spots and orientation angle data information of the vehicle spots, clustering and roughly grouping the parking spots according to the orientation angle data information of the vehicle spots, and outputting rough grouping data information of the vehicle spots;
q2, inputting the coordinate data information of the vehicle position into a vehicle position same-row offset distance algorithm to carry out fine grouping on the vehicle position based on the rough grouping data information of the vehicle position, and outputting the fine grouping data information of the vehicle position;
q3. based on the refined grouping data information of the parking spots, performing linear least square fitting on two near car spots of all the parking spots in the same group, and outputting fitting linear data information of the parking spots in the same group;
and Q4, optimizing the coordinate data information of the parking spots, the orientation angle data information of the vehicle spots and the central point coordinate data information of the vehicle spots based on the fitting straight line data information of the parking spots in the same group, and outputting the optimized parking spot data information.
In this embodiment, in step Q3, the performing a straight line minimum fitting on two near points of the parking space in the same group includes:
q31, acquiring near-vehicle-point coordinate data information of vehicle points in the same group based on the precise group data information of the vehicle points;
q32 based on the coordinate data information of the near points of the same group of vehicle points, adopting a least square algorithm to perform straight line fitting to obtain the slope k and intercept b of the fitted straight line,
，
，
wherein N is the number of car-loci of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The coordinates of the near vehicle point of the ith vehicle point;
and Q33, obtaining fitting straight line data information of the parking spaces in the same group based on the slope k and the intercept b of the fitting straight line.
In this embodiment, in step Q4, the optimized parking spot data information includes near-spot coordinates of the optimized parking spotAnd->，
，/>，
Wherein k is the slope of the fitting line in the fitting line data information of the parking spaces of the same group, b is the intercept of the fitting line in the fitting line data information of the parking spaces of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The near car point coordinates of the i-th car point.
In this embodiment, the optimized parking spot data information further includes a parking spot orientation angle θ of the optimized vehicle spot,
，
wherein,and->And the near-vehicle-point coordinates of the optimized vehicle-point are obtained.
In this embodiment, the optimized vehicleThe location data information also comprises the far car point coordinates of the optimized car locationAnd->Parking space center coordinates +.>，
，/>，
，
Wherein,and->For the near-vehicle-point coordinates of the optimized vehicle-point, θ is the parking-space orientation angle of the optimized vehicle-point, and L is +.>And->Is a distance between the two.
The application provides a post-optimization system of a parking space detection point, which comprises computer equipment, wherein the computer equipment is programmed or configured to execute the steps of the post-optimization method of any parking space detection point.
The present application provides a computer readable storage medium having stored thereon a computer program programmed or configured to perform the post-optimization method of any one of the stall detection points.
Any reference to memory, storage, database, or other medium used in embodiments of the application may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
In summary, the method for optimizing the multi-parking-space grouping is provided after the parking space data are obtained through sensing fusion, more accurate and more reasonable parking space output is provided, and stable and accurate parking space data support is provided for functional modules such as path planning and the like in a parking automatic driving system.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. A post-optimization method for a parking spot detection point, the method comprising:
q1. collecting data information of parking spots under a world coordinate system in the same parking lot, wherein the data information of the parking spots comprises coordinate data information of the vehicle spots and orientation angle data information of the vehicle spots, clustering and roughly grouping the parking spots according to the orientation angle data information of the vehicle spots, and outputting rough grouping data information of the vehicle spots;
q2, inputting the coordinate data information of the vehicle position into a vehicle position same-row offset distance algorithm to carry out fine grouping on the vehicle position based on the rough grouping data information of the vehicle position, and outputting the fine grouping data information of the vehicle position;
q3. based on the refined grouping data information of the parking spots, performing linear least square fitting on two near car spots of all the parking spots in the same group, and outputting fitting linear data information of the parking spots in the same group;
q4, optimizing the coordinate data information of the parking spots, the orientation angle data information of the vehicle spots and the central point coordinate data information of the vehicle spots based on the fitting straight line data information of the parking spots in the same group, and outputting the optimized parking spot data information;
in step Q2, the vehicle-site in-line offset distance algorithm includes:
q21 obtaining two coordinates P of the near vehicle point in the width direction of the ith vehicle position point according to the coordinate data information of the vehicle position point i1 (X i1 ,Y i1 0), and P i2 (X i2 ,Y i2 0) and two near-vehicle-point coordinates P in the width direction of the jth parking spot j1 (X j1 ,Y j1 0), and P j2 (X j2 ,Y j2 ,0)；
Q22 based on the two near-vehicle-point coordinates P in the width direction of the ith vehicle-position point i1 And P i2 Two near-vehicle-point coordinates P in width direction of jth parking spot j1 And P j2 Two near vehicle points P of the jth vehicle point are established j1 And P j2 Respectively to line segment P i1 P i2 Projection distance function d of (2) j1 And d j2 ；
Q23 based on the projection distance function d j1 And d j2 Setting a preset threshold value, if d j1 And d j2 The values of the (b) are smaller than the preset threshold value, and the ith vehicle position and the jth vehicle position are the same row of parking spaces.
2. The post-optimization method of parking space detection points according to claim 1, wherein in the step Q1, the parking space points are clustered and roughly grouped according to the orientation angle of the parking space according to the orientation angle data information of the vehicle position points, the orientation angles of the parking spaces of the same parking space type are consistent, and the parking space type comprises a vertical parking space, a horizontal parking space and an oblique parking space.
3. The post-optimization method of parking spot according to claim 1, wherein in step Q2, two near points P of the jth vehicle point are established j1 And P j2 Respectively to line segment P i1 P i2 Projection distance function d of (2) j1 And d j2 The method comprises the following steps:
，/>，
wherein W is two near-vehicle point coordinates P i1 And P i2 Distance L of (2) 11 、L 12 、L 21 And L 22 Respectively the parameters of projection distance S 1 And S is 2 Is a distance difference factor.
4. The post-optimization method of parking spot detection points according to claim 1, wherein: the precise grouping data information of the parking spots is the parking spot data information of the same row, wherein the orientation angles of the parking spots in the same grouping are consistent.
5. The post-optimization method of parking spot detection points according to claim 1, wherein in step Q3, the performing a straight line minimum fitting on two near-car points of the same group of parking spots includes:
q31, acquiring near-vehicle-point coordinate data information of vehicle points in the same group based on the precise group data information of the vehicle points;
q32 based on the coordinate data information of the near points of the same group of vehicle points, adopting a least square algorithm to perform straight line fitting to obtain the slope k and intercept b of the fitted straight line,
，
，
wherein N is the number of car-loci of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The coordinates of the near vehicle point of the ith vehicle point;
and Q33, obtaining fitting straight line data information of the parking spaces in the same group based on the slope k and the intercept b of the fitting straight line.
6. The post-optimization method of parking spot according to claim 5, wherein in step Q4, the optimized parking spot data information includes near-spot coordinates of the optimized parking spotAnd->，
，/>，
Wherein k is the slope of the fitting line in the fitting line data information of the parking spaces of the same group, b is the intercept of the fitting line in the fitting line data information of the parking spaces of the same group, (X) i1 ,Y i1 ) And (X) i2 ,Y i2 ) The near car point coordinates of the i-th car point.
7. The post-optimization method of a parking spot according to claim 6, wherein the optimized parking spot data information further includes an optimized parking spot orientation angle θ of the vehicle spot,
，
wherein,and->And the near-vehicle-point coordinates of the optimized vehicle-point are obtained.
8. The post-optimization method of parking spot according to claim 7, wherein the optimized parking spot data information further includes far spot coordinates of the optimized parking spotAnd->Central coordinates of parking space，
，/>，
，
Wherein,and->For the near-vehicle-point coordinates of the optimized vehicle-point, θ is the parking-space orientation angle of the optimized vehicle-point, and L is +.>And->Is a distance between the two.
9. A post-optimization system for a stall detection point comprising computer equipment, characterized in that the computer equipment is programmed or configured to perform the steps of the post-optimization method for a stall detection point according to any one of claims 1-8.
10. A computer readable storage medium having stored thereon a computer program programmed or configured to perform the post-optimization method of a stall detection point of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311267169.9A CN117012053A (en) | 2023-09-28 | 2023-09-28 | Post-optimization method, system and storage medium for parking space detection point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311267169.9A CN117012053A (en) | 2023-09-28 | 2023-09-28 | Post-optimization method, system and storage medium for parking space detection point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117012053A true CN117012053A (en) | 2023-11-07 |
Family
ID=88562155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311267169.9A Pending CN117012053A (en) | 2023-09-28 | 2023-09-28 | Post-optimization method, system and storage medium for parking space detection point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117012053A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100112924A (en) * | 2009-04-10 | 2010-10-20 | 주식회사 만도 | Method and system for recongnizing target position for parallel parking |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN107133591A (en) * | 2017-05-05 | 2017-09-05 | 深圳前海华夏智信数据科技有限公司 | Method for detecting parking stalls and device based on structure light |
| CN108986122A (en) * | 2018-08-01 | 2018-12-11 | 重庆大学 | Indoor parking guidance map intelligent reconstruction method |
| CN110472580A (en) * | 2019-08-16 | 2019-11-19 | 北京茵沃汽车科技有限公司 | The method, apparatus of detection parking stall based on full-view image, storage medium |
| US11002859B1 (en) * | 2020-02-27 | 2021-05-11 | Tsinghua University | Intelligent vehicle positioning method based on feature point calibration |
| US20210390855A1 (en) * | 2020-06-12 | 2021-12-16 | Parkling Gmbh | Method for determining an occupancy status of a parking bay and for determining the occupancy statuses of several parking bays along a street |
| CN114758318A (en) * | 2022-02-21 | 2022-07-15 | 北京航空航天大学 | Method for detecting parking stall at any angle based on panoramic view |
| CN115240154A (en) * | 2022-06-29 | 2022-10-25 | 高德软件有限公司 | Method, device, equipment and medium for extracting point cloud features of parking lot |
| CN115339436A (en) * | 2021-05-14 | 2022-11-15 | 上海汽车集团股份有限公司 | Method and related device for correcting parking space angular point |
| WO2022266854A1 (en) * | 2021-06-22 | 2022-12-29 | 华为技术有限公司 | Parking space detection method and device |
| CN115861417A (en) * | 2022-09-07 | 2023-03-28 | 北京地平线信息技术有限公司 | Parking space reconstruction method and device, electronic equipment and storage medium |
| CN116385999A (en) * | 2023-02-20 | 2023-07-04 | 北京四维图新科技股份有限公司 | Parking space identification method, device and equipment |
| CN116778458A (en) * | 2023-08-23 | 2023-09-19 | 苏州魔视智能科技有限公司 | Parking space detection model construction method, parking space detection method, equipment and storage medium |
-
2023
- 2023-09-28 CN CN202311267169.9A patent/CN117012053A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100112924A (en) * | 2009-04-10 | 2010-10-20 | 주식회사 만도 | Method and system for recongnizing target position for parallel parking |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN107133591A (en) * | 2017-05-05 | 2017-09-05 | 深圳前海华夏智信数据科技有限公司 | Method for detecting parking stalls and device based on structure light |
| CN108986122A (en) * | 2018-08-01 | 2018-12-11 | 重庆大学 | Indoor parking guidance map intelligent reconstruction method |
| CN110472580A (en) * | 2019-08-16 | 2019-11-19 | 北京茵沃汽车科技有限公司 | The method, apparatus of detection parking stall based on full-view image, storage medium |
| US11002859B1 (en) * | 2020-02-27 | 2021-05-11 | Tsinghua University | Intelligent vehicle positioning method based on feature point calibration |
| US20210390855A1 (en) * | 2020-06-12 | 2021-12-16 | Parkling Gmbh | Method for determining an occupancy status of a parking bay and for determining the occupancy statuses of several parking bays along a street |
| CN115339436A (en) * | 2021-05-14 | 2022-11-15 | 上海汽车集团股份有限公司 | Method and related device for correcting parking space angular point |
| WO2022266854A1 (en) * | 2021-06-22 | 2022-12-29 | 华为技术有限公司 | Parking space detection method and device |
| CN114758318A (en) * | 2022-02-21 | 2022-07-15 | 北京航空航天大学 | Method for detecting parking stall at any angle based on panoramic view |
| CN115240154A (en) * | 2022-06-29 | 2022-10-25 | 高德软件有限公司 | Method, device, equipment and medium for extracting point cloud features of parking lot |
| CN115861417A (en) * | 2022-09-07 | 2023-03-28 | 北京地平线信息技术有限公司 | Parking space reconstruction method and device, electronic equipment and storage medium |
| CN116385999A (en) * | 2023-02-20 | 2023-07-04 | 北京四维图新科技股份有限公司 | Parking space identification method, device and equipment |
| CN116778458A (en) * | 2023-08-23 | 2023-09-19 | 苏州魔视智能科技有限公司 | Parking space detection model construction method, parking space detection method, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 仇旭;朱浩;邓元望;: "基于超声波雷达的改进车位检测算法研究", 中国机械工程, no. 14, pages 113 - 119 * |
| 杨科;张效宇;徐维庆;: "基于卷积神经网络的环视车位检测研究", 时代汽车, no. 04, pages 6 - 9 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110531753B (en) | Control system, control method and controller for autonomous vehicle | |
| US20180074506A1 (en) | Systems and methods for mapping roadway-interfering objects in autonomous vehicles | |
| CN109631896B (en) | Parking lot autonomous parking positioning method based on vehicle vision and motion information | |
| CN110126817B (en) | Method and system for self-adapting to parking or recalling between any point and fixed point | |
| CN110103953B (en) | Method, apparatus, medium, and system for assisting driving control of vehicle | |
| DE102018113007A1 (en) | TRAJECTOR PLANNER FOR AUTONOMOUS DRIVING BY BÉZIER CURVES | |
| DE102019112002A1 (en) | SYSTEMS AND METHOD FOR THE AUTOMATIC DETECTION OF PENDING FEATURES | |
| US10467487B1 (en) | Fusion-based traffic light recognition for autonomous driving | |
| CN110163930A (en) | Lane line generation method, device, equipment, system and readable storage medium storing program for executing | |
| CN111319612B (en) | Self-map building method and system for map for automatic driving vehicle | |
| US20170364759A1 (en) | Systems and methods for determining the presence of traffic control personnel and traffic control signage | |
| CN114051628B (en) | Method and device for determining target object point cloud set | |
| US20200070822A1 (en) | Systems and methods for predicting object behavior | |
| CN113095216A (en) | Parking monitoring method, system, equipment and storage medium | |
| CN113895464A (en) | Intelligent vehicle driving map generation method and system fusing personalized driving style | |
| CN114898322A (en) | Driving environment identification method and device, vehicle and storage medium | |
| CN114495045A (en) | Sensing method, sensing device, sensing system and related equipment | |
| Song et al. | Automatic detection and classification of road, car, and pedestrian using binocular cameras in traffic scenes with a common framework | |
| Gong et al. | Pedestrian detection method based on roadside light detection and ranging | |
| CN113895429A (en) | Automatic parking method, system, terminal and storage medium | |
| CN117012053A (en) | Post-optimization method, system and storage medium for parking space detection point | |
| CN112912894A (en) | Road boundary identification method and device | |
| CN116258174A (en) | System and method for detecting inference quality of deep neural network | |
| CN113135179A (en) | Parking detection method, device, equipment, system and storage medium | |
| CN117496483B (en) | Night image recognition method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |